Hichem Kallel

Hichem Kallel

Auto-generated profile, based on publicly available information

Hichem Kallel

Mediterranean Institute of Technology, Southern Mediterranean University, Tunis 1053, Tunisia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2023 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
NWNesrine Wagaa
Nesrine Wagaa
HKHichem Kallel
Hichem Kallel
NMNédra Mellouli
Nédra Mellouli

11 January 2022 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
NWNesrine Wagaa
Nesrine Wagaa
HKHichem Kallel
Hichem Kallel
NMNédra Mellouli
Nédra Mellouli
Handwritten characters recognition is a challenging research topic. A lot of works have been present to recognize letters of different languages. The availability of Arabic handwritten characters databases is limited. Motivated by this topic of research, we propose a convolution neural network for the classification of Arabic handwritten letters. Also, seven optimization algorithms are performed, and the best algorithm is reported. Faced with few available Arabic handwritten datasets, various data augmentation techniques are implemented to improve the robustness needed for the convolution neural network model. The proposed model is improved by using the dropout regularization method to avoid data overfitting problems. Moreover, suitable change is presented in the choice of optimization algorithms and data augmentation approaches to achieve a good performance. The model has been trained on two Arabic handwritten characters datasets AHCD and Hijja. The proposed algorithm achieved high recognition accuracy of 98.48% and 91.24% on AHCD and Hijja, respectively, outperforming other state-of-the-art models.

8 November 2025 in Sensors
Verified
Journal Article
Open access
PDF file
HKHichem Kallel
Hichem Kallel
Kamran IqbalKamran Iqbal
Kamran Iqbal
Traditional control of robotic systems relies on the availability of an exact model, which assumes complete knowledge of the robot’s parameters and all dynamic effects. However, this idealized scenario rarely holds in practice, as real-world interactions introduce unpredictable environmental influences, friction, and edge effects. This paper presents a novel data-driven approach to modeling and estimating robot dynamics by leveraging data collected during the robot’s movements. The proposed method operates without prior knowledge of the system parameters, thereby addressing the limitations of conventional model-based control strategies in complex and uncertain environments. Our unified data-driven framework integrates classical control theory with modern machine learning techniques, including system identification, physics-informed neural networks (PINNs), and deep learning. We demonstrate its efficacy in the case of a two-link robotic manipulator that achieves superior trajectory tracking and robustness to unmodeled dynamics. The technique is modular and can be extended to manipulators with more joints.

2 August 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
NWNesrine Wagaa
Nesrine Wagaa
HKHichem Kallel
Hichem Kallel
A Robot dynamic analysis defines mathematical equations that describe the relationship between robot motion and torques. Newton-Euler and Lagrange-Euler are methods to determine the dynamic model. The performance of robot dynamic control depends on many factors, such as estimation of dynamic parameters, computation complexity, inaccuracy of the friction model parameters, simplification of the robot model, redundancy, etc. This paper implemented several Deep Learning architectures to model and establish dynamic control to overcome the problems of robustness and unmodeled dynamics. The proposed Deep Learning networks are Artificial Neural Networks, Convolutional Neural Networks, Long-short-term, Gated Recurrent units, and Bidirectional. In this context, we associate the achieved Deep learning models’ performances with specific tuning hyper-parameters such as the number of artificial neurons in hidden layers, number of hidden layers, optimization algorithms, number of epochs, attention mechanism, etc. The Bidirectional Long-short-term memory model outperformed all proposed networks. To be as close as possible to the experimental results, we add three types of noise (Uniform, Heteroscedastic, and Functional) to the training dataset to verify which of the five proposed neural networks is more effective. Furthermore, we evaluate the influence of geometric robotic complexity on the DL models’ performance. In this work, we also propose a new non-linear motion control technique. We conduct tests using numerical and deep learning methods to comprehensively verify the effectiveness and robustness of the proposed nonlinear control technique.